We introduce a spatially dense variational approach to estimate the calibration of multiple cameras in the context of 3D reconstruction. We propose a relaxation scheme which allow...
We propose a mid-level statistical model for image segmentation that composes multiple figure-ground hypotheses (FG) obtained by applying constraints at different locations and s...
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
Acquiring transparent, refractive objects is challenging as these kinds of objects can only be observed by analyzing the distortion of reference background patterns. We present a ...
Gordon Wetzstein, David Roodnick, Wolfgang Heidric...
Abstract. This paper presents an expressive gesture model that generates communicative gestures accompanying speech for the humanoid robot Nao. The research work focuses mainly on ...